© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38466
    Prev
    Next
    INDEX
    Explanations

    phase transitions and analyses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¥
    -0.09
    shire
    -0.09
    ness
    -0.09
    -fashioned
    -0.08
    ÏĤ
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    tings
    -0.08
    shaw
    -0.08
    ìļĶ
    -0.07
    æ¯Ķãģ¹ãĤĭãģ¨
    -0.07
    POSITIVE LOGITS
    oenix
    0.12
     بÙĨدÛĮ
    0.10
    hift
    0.09
    araoh
    0.08
    istol
    0.08
    ãĢħãģ¨
    0.08
    less
    0.08
    менÑĤиÑĢов
    0.08
    ylum
    0.08
    ãģĺãĤģãģ¦
    0.08
    Activations Density 0.039%

    No Known Activations